Identification of the nonlinear steering dynamics of an autonomous vehicle
This addresses the need for precise vehicle-specific models in automated driving applications, though it is incremental as it applies an existing method to a new domain.
The paper tackled the problem of accurately modeling the nonlinear steering dynamics of an autonomous vehicle using data-driven methods, demonstrating that a neural network-based subspace-encoder method successfully captured the dynamics where other methods failed.
Automated driving applications require accurate vehicle specific models to precisely predict and control the motion dynamics. However, modern vehicles have a wide array of digital and mechatronic components that are difficult to model, manufactures do not disclose all details required for modelling and even existing models of subcomponents require coefficient estimation to match the specific characteristics of each vehicle and their change over time. Hence, it is attractive to use data-driven modelling to capture the relevant vehicle dynamics and synthesise model-based control solutions. In this paper, we address identification of the steering system of an autonomous car based on measured data. We show that the underlying dynamics are highly nonlinear and challenging to be captured, necessitating the use of data-driven methods that fuse the approximation capabilities of learning and the efficiency of dynamic system identification. We demonstrate that such a neural network based subspace-encoder method can successfully capture the underlying dynamics while other methods fall short to provide reliable results.